Page 3 of 5

Blog

Thoughts on AI engineering, responsible automation, and building systems that matter.

April 2025·Developer Tools·10 min read

How I use Git worktrees to work on 4 things at once without losing my mind

I had a production hotfix, two feature branches, and a code review all due by end of day. Stashing was not going to cut it.

April 2026·Engineering Stories·12 min read

The hardest bug I ever fixed took three days and zero lines of code

The bug crashed production every Tuesday at 2 AM. Only Tuesday. Only 2 AM. The logs showed nothing. The monitoring showed nothing. Three days later I found it - and the fix was not code.

May 2026·AI Engineering·12 min read

How I test AI-generated code before I trust it

AI can write code quickly. That does not make the code safe, maintainable, or production-ready. Over time I built a testing workflow that treats AI output like a fast junior teammate: useful, productive, and never above verification.

June 2026·AI Engineering·12 min read

Human-in-the-loop is not a fallback. It is the product.

The strongest automation systems I trust are not the ones that pretend humans disappeared. They are the ones that know exactly when a human should stay in the loop, what decision that human should make, and how the system should continue afterward.

July 2026·PHP & Laravel·12 min read

Is Laravel too magical?

Laravel gets called magical when it hides work developers expected to see. After years of building PHP systems, I think the real question is not whether Laravel has magic. It is whether your team knows where the magic ends.

July 2026·PHP & Laravel·12 min read

Why Laravel queues are the backbone of reliable AI automation

An AI feature can look impressive in a request-response demo and still collapse in production. Queues turn slow, unpredictable model calls into workflows that can be retried, inspected, limited, and trusted.

February 2026·Developer Tools·11 min read

Why I chose Laravel Zero for a CLI tool - and what it taught me about framework selection

I needed to build a CLI tool that could orchestrate Docker containers, manage Git worktrees, allocate ports, and run a 9-stage pipeline in under a minute. I evaluated five options. The winner surprised me.

December 2025·Career·9 min read

Why I study Law while building AI systems

The first time a lawyer asked me "but who is liable when the AI makes a wrong decision?" I realized I had been building systems without understanding the world they operate in.